AidervsQwen Code
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Aider
Aider AI (Paul Gauthier) · Terminal agent
#7OSS
Panel
7.12 spec wins
- Reliability
- 7.2
- Usefulness
- 6.8
- Cost
- 7.5
- Longevity
- 7.0
“Commits every change to git so you can see exactly which one broke the build.”
Qwen Code
Alibaba Cloud (Qwen) · Terminal agent
#19OSSMCP
Panel
6.83 spec wins
- Reliability
- 6.5
- Usefulness
- 6.8
- Cost
- 7.3
- Longevity
- 6.3
“Ships a Java SDK, which tells you precisely which enterprises Alibaba expects to pay for it.”
Spec by spec
| Spec | Aider | Qwen Code |
|---|---|---|
| Architecture | ||
| Category | Terminal agent | Terminal agent |
| Runs | local | local |
| Platforms | macos, linux, windows | macos, linux, windows |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | No | Yes |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | Yes | Yes |
| Git operations | Yes | Yes |
| Browser control | YesThe /web command and URL detection drive a real Chromium through Playwright to render and read pages (--disable-playwright turns it off); the --browser flag is only aider's own Streamlit GUI. | YesThe first-party @qwen-code/chrome-bridge extension tunnels cdp_* frames from the `qwen serve` daemon into chrome.debugger so the agent drives a real Chrome tab, but console/network/screenshot/click tools need an external CDP MCP adapter set via QWEN_CDP_MCP_COMMAND, since none is bundled. |
| Sandboxed execution | NoAider publishes a Docker image as an install option only; commands it runs are not sandboxed. | YesTwo real isolation modes - macOS Seatbelt via sandbox-exec (default `permissive-open` profile) and container-based Docker/Podman with a published sandbox image (https://qwenlm.github.io/qwen-code-docs/en/users/features/sandbox/). |
| Multi-agent orchestration | No | Yes |
| Headless / CI mode | Yes | Yes |
| Models | ||
| Backbone | OpenAI, Anthropic, Gemini, DeepSeek, OpenRouter, Bedrock, Vertex AI, Azure, Groq, xAI, Ollama, LM Studio | Qwen3-Coder, OpenAI-compatible, Claude, Gemini |
| Bring your own model | Yes | Yes |
| Local models | Yes | Yes |
| Cost | ||
| Pricing model | byok | byok |
| Starts at | $0/mo | n/a |
| Free tier | Yes | No |
| Bring your own key | Yes | Yes |
| Openness | ||
| Open source | Yes | Yes |
| License | Apache-2.0 | Apache-2.0 |
| GitHub stars | 49,324 | 28,271 |
Which one would each critic pick
| Critic | Aider | Qwen Code | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.5 | 7.0 | Aider — Pick Aider if you want to see every diff and steer every step; pick Claude Code if you want the agent to find the files and run on its own. |
| El Crítico | 7.3 | 6.3 | Aider — Every edit is a real edit on your disk with no sandbox, and auto-commit is the one mitigation standing between a bad command and your afternoon. |
| El Profesor | 8.3 | 6.0 | Aider — The most legible architecture on the board, with a published harness; the SWE-bench numbers are from 2024 and should be read as history, not as a claim. |
| La Inversora | 5.3 | 6.8 | Qwen Code — Alibaba killed the Qwen OAuth free tier on 2026-04-15, the classic subsidy-to-subscription turn, and 27,000 stars now have to pay someone. |
| La Jefa | 5.5 | 5.8 | Qwen Code — No seat and nothing to sign; the Coding Plan is a weekly quota on Alibaba Cloud with a Beijing or an international endpoint, and legal will ask which one sixty laptops point at. |
| El Hacker | 9.0 | 8.8 | Aider — Python I can read, prompts in the repo, .aider.conf.yml for model and edit format, --model ollama/anything for an air-gapped box; MCP is the one gap. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.